{"id":"https://openalex.org/W4312282783","doi":"https://doi.org/10.1109/iros47612.2022.9981999","title":"Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space","display_name":"Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312282783","doi":"https://doi.org/10.1109/iros47612.2022.9981999"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981999","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113787478","display_name":"Kuan Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kuan Fang","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030238910","display_name":"Patrick Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Yin","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021472921","display_name":"Ashvin Nair","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashvin Nair","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113787478"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.4552,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84351433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4076","last_page":"4083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8048359155654907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7866185307502747},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.692779004573822},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6671017408370972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5387137532234192},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5040192008018494},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4649468958377838},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4639643430709839},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4267379641532898},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42486098408699036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4230485260486603},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41365569829940796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08734425902366638},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08437168598175049}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8048359155654907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866185307502747},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.692779004573822},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6671017408370972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5387137532234192},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5040192008018494},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4649468958377838},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4639643430709839},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4267379641532898},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42486098408699036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4230485260486603},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41365569829940796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08734425902366638},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08437168598175049},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981999","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3484629716","display_name":null,"funder_award_id":"FA9550-22-1-0273","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5469137442","display_name":null,"funder_award_id":"W911NF-17-2-0181","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6661146833","display_name":null,"funder_award_id":"W911NF-21-1-0097","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1594201624","https://openalex.org/W1901129140","https://openalex.org/W1971086298","https://openalex.org/W2019965290","https://openalex.org/W2128990851","https://openalex.org/W2141841102","https://openalex.org/W2161819990","https://openalex.org/W2188365844","https://openalex.org/W2337392266","https://openalex.org/W2525579820","https://openalex.org/W2752796333","https://openalex.org/W2823112946","https://openalex.org/W2947150733","https://openalex.org/W2962736495","https://openalex.org/W2963439114","https://openalex.org/W2963799213","https://openalex.org/W2970377754","https://openalex.org/W2970393539","https://openalex.org/W2982432464","https://openalex.org/W3008970887","https://openalex.org/W3028695364","https://openalex.org/W3033324992","https://openalex.org/W3035717769","https://openalex.org/W3035850588","https://openalex.org/W3040490156","https://openalex.org/W3101007912","https://openalex.org/W3123614573","https://openalex.org/W3126916000","https://openalex.org/W3127454018","https://openalex.org/W3129049380","https://openalex.org/W3171176697","https://openalex.org/W3172360140","https://openalex.org/W3205794883","https://openalex.org/W3207837114","https://openalex.org/W3208796191","https://openalex.org/W3210048194","https://openalex.org/W3212887262","https://openalex.org/W4286858772","https://openalex.org/W4287066693","https://openalex.org/W4287209565","https://openalex.org/W4287756699","https://openalex.org/W4288021424","https://openalex.org/W4288109092","https://openalex.org/W4288331462","https://openalex.org/W4300799055","https://openalex.org/W4362590704","https://openalex.org/W6616173779","https://openalex.org/W6635701881","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6696955428","https://openalex.org/W6740801417","https://openalex.org/W6753060773","https://openalex.org/W6757469721","https://openalex.org/W6760560886","https://openalex.org/W6763704811","https://openalex.org/W6764173040","https://openalex.org/W6765008394","https://openalex.org/W6767047803","https://openalex.org/W6767246565","https://openalex.org/W6767649332","https://openalex.org/W6768220214","https://openalex.org/W6769035977","https://openalex.org/W6769166761","https://openalex.org/W6769673253","https://openalex.org/W6774967489","https://openalex.org/W6778594666","https://openalex.org/W6779265984","https://openalex.org/W6779463497","https://openalex.org/W6779830607","https://openalex.org/W6785279338","https://openalex.org/W6785353143","https://openalex.org/W6796589144","https://openalex.org/W6797805403","https://openalex.org/W6801798027","https://openalex.org/W6802659552","https://openalex.org/W6803644249"],"related_works":["https://openalex.org/W1568779110","https://openalex.org/W804484174","https://openalex.org/W4244698559","https://openalex.org/W4246538999","https://openalex.org/W56933075","https://openalex.org/W2002361198","https://openalex.org/W99657755","https://openalex.org/W2998826171","https://openalex.org/W2036736859","https://openalex.org/W3213722473"],"abstract_inverted_index":{"General-purpose":[0],"robots":[1],"require":[2,75],"diverse":[3],"repertoires":[4],"of":[5,35,79,197,224],"behaviors":[6,200],"to":[7,23,48,58,67,81,177,230],"complete":[8],"challenging":[9],"tasks":[10,36,73,172,206],"in":[11,110,182,189,210],"real-world":[12],"unstructured":[13],"environments.":[14],"To":[15],"address":[16],"this":[17,53],"issue,":[18],"goal-conditioned":[19,41,69],"reinforcement":[20,142],"learning":[21],"aims":[22],"acquire":[24],"policies":[25,42,70],"that":[26,63,74,102,173,207,218,226],"can":[27,220],"reach":[28],"configurable":[29],"goals":[30],"for":[31,71,114,203],"a":[32,61,99,115,122],"wide":[33],"range":[34],"on":[37,87,136,195],"command.":[38],"However,":[39],"such":[40],"are":[43,174,208],"notoriously":[44],"difficult":[45],"and":[46,133,144,186,201],"time-consuming":[47],"train":[49,68],"from":[50],"scratch.":[51],"In":[52],"paper,":[54],"we":[55,92,120],"propose":[56,121],"Planning":[57],"Practice":[59],"(PTP),":[60],"method":[62],"makes":[64],"it":[65],"practical":[66],"long-horizon":[72],"multiple":[76],"distinct":[77],"types":[78],"interactions":[80],"solve.":[82],"Our":[83,214],"approach":[84,124],"is":[85,155,193],"based":[86],"two":[88],"key":[89],"ideas.":[90],"First,":[91],"decompose":[93],"the":[94,111,129,134,147,159,165,184,191,211,228,233],"goal-reaching":[95,171],"problem":[96],"hierarchically,":[97],"with":[98],"high-level":[100],"planner":[101],"sets":[103],"intermediate":[104],"subgoals":[105,225],"using":[106],"conditional":[107,130],"subgoal":[108,131],"generators":[109],"latent":[112],"space":[113],"low-level":[116],"model-free":[117],"policy.":[118],"Second,":[119],"hybrid":[123],"which":[125,162,190],"first":[126],"pre-trains":[127],"both":[128,183],"generator":[132],"policy":[135,148,192,229],"previously":[137],"collected":[138],"data":[139],"through":[140],"offline":[141,212],"learning,":[143],"then":[145],"fine-tunes":[146],"via":[149],"online":[150],"exploration.":[151],"This":[152],"fine-tuning":[153],"process":[154],"itself":[156],"facilitated":[157],"by":[158],"planned":[160],"subgoals,":[161],"breaks":[163],"down":[164],"original":[166],"target":[167,234],"task":[168],"into":[169],"short-horizon":[170],"significantly":[175],"easier":[176],"learn.":[178],"We":[179],"conduct":[180],"experiments":[181],"simulation":[185],"real":[187],"world,":[188],"pre-trained":[194],"demonstrations":[196],"short":[198],"primitive":[199],"fine-tuned":[202],"temporally":[204],"extended":[205],"unseen":[209],"data.":[213],"experimental":[215],"results":[216],"show":[217],"PTP":[219],"generate":[221],"feasible":[222],"sequences":[223],"enable":[227],"efficiently":[231],"solve":[232],"tasks.":[235],"<sup":[236,239],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[237,240],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[238,241],"Supplementary":[242],"video:":[243],"sites.google.com/view/planning-to-practice":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}